Industry self-adaptive intelligent search method

An intelligent search and adaptive technology, which is applied in special data processing applications, natural language data processing, unstructured text data retrieval, etc., can solve the problems of limited search range, poor adaptive ability, and high degree of customization of search systems. Achieve the effect of improving search quality, reducing impact, and improving flexibility

Pending Publication Date: 2020-07-28
SHANDONG SYNTHESIS ELECTRONICS TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The classification of the industry system is clear, and the search results are guaranteed, but the search scope is limited
Due to the close relationship between the industry search system and vertical industry business, the industry-oriented search system has a high degree of customization and poor adaptability

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Industry self-adaptive intelligent search method
  • Industry self-adaptive intelligent search method
  • Industry self-adaptive intelligent search method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] This embodiment discloses an industry-adaptive intelligent search method, such as figure 1 , 2 shown, including the following steps:

[0031] S01), data collection, collect the original book information of the target industry through web crawlers, industry laws and regulations documents, etc. and save it in the database. Specifically, web page data is crawled on websites with information related to the target industry, limited government official websites or industry representative websites ensure the authenticity of data information, and at the same time establish download and update strategies, start regular update tasks, and ensure the real-time nature of data information .

[0032] For the target industry, artificially actively collect relevant laws and regulations or require target customers to provide industry desensitization information, actual implementation measures and implementation methods of the policy, so as to make the data more authentic and operable. ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an industry self-adaptive intelligent search method. According to the method, by dividing service words and general words, the weight of the service words is increased, the weight of the general words is reduced, and the influence of words with low topic correlation on search results is reduced. The validity threshold and the uniqueness threshold are automatically updated,and the flexibility of a search system is improved. And hierarchical search improves the search efficiency. And factors such as sentence geometrical characteristics, word edge distribution, word topicjoint distribution and word distribution semantics are combined, so that the matching degree of search and a target topic is improved, and the search quality is improved. A self-learning feedback mechanism based on search results supports iterative optimization of the search method.

Description

technical field [0001] The invention relates to an industry-adaptive intelligent search method, which belongs to the technical field of artificial intelligence. Background technique [0002] With the explosive development of the Internet, all kinds of information on the Internet have grown exponentially, which has caused the information users want to query to be lost in the huge and complicated Internet big data. How to effectively improve the user's search efficiency and search quality has become the focus. [0003] At present, there are no more than two channels for users to obtain information. One is to obtain information through general search similar to Google and Baidu, but the search results often include information in various aspects, and users need to perform secondary screening and judgment. High, and the authenticity and timeliness of the information cannot be guaranteed. [0004] The second is to obtain relatively professional and accurate information through ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F16/33G06F40/289G06F40/30
CPCG06F16/3335G06F16/3344Y02D10/00
Inventor 李民朱锦雷张传锋
Owner SHANDONG SYNTHESIS ELECTRONICS TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products